Publish the counted chart. Card text and png only. Weights unchanged.

README.md

@@ -35,4 +35,4 @@ measurements, not deployment guarantees.
 
 ![Can Small Security Models Stop Prompt Injection — And Is Fine-Tuning Worth It?](jev_human_questions_chart.png)
 
-Chart corrected 2026-11-05 after two independent audits against primary records (live AgentDojo JSONL recounts and per-row score recomputes). One threshold and mode per row; summary-only cells are labeled on the chart. Replication report regenerated with zero diff before publication.
+Checked 2026-11-05 against the live run3 counts and the per-row score files. Q1 row 2 is stop replay at 0.99: 51/249 tasks finished, 7/249 hijacked, 35/37 normal tasks passed, adaptive 53/100. The judge normal rate is 141/148. No per-check timing is on the chart. CLEF-Screen caught 20098/20271 (99.1%). `build_replication_package.py` rerun matched the published AUCs. Two gaps stay labeled: CLEF-DualScreen has no local per-row test file, and the SecJev redo numbers are bench draws.